Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Failure Detection and Reasoning on RLBench
Loading...
91.7
Detection Accuracy
ARMOR
3.3
26.25
49.2
72.15
Feb 12, 2026
Detection Accuracy
LLM Fuzzy Score
ROUGEL
Updated 1mo ago
Evaluation Results
Method
Method
Links
Detection Accuracy
LLM Fuzzy Score
ROUGEL
ARMOR
2026.02
91.7
71.8
80.2
SFT-S+D
2026.02
72.6
55
64.6
SFT-D
2026.02
64
46
60.6
Claude-3.7
shots=3
2026.02
56.1
47.3
52.6
Claude-3.7
shots=0
2026.02
42
37.2
33.6
Qwen2.5-VL
shots=0
2026.02
37.6
25.5
35.3
Cosmos-Reasoning
2026.02
31.7
22
14
LLaVA-NeXT
2026.02
6.7
34.6
3.2
Feedback
Search any
task
Search any
task